Imad Eddine Berjamy's Work | ContraWork by Imad Eddine BerjamyImad Eddine Berjamy
AI Engineer | UiPath RPA Consultant | AI Agents & Python
why every #AI engineer needs #Pydantic:
LLMs don’t return data. They return text that looks like data, most of the time. And “most of the time” is how production systems break.
I made a 6-minute video on why Pydantic is the one library every AI engineer should know:
→ One class does three jobs: it tells the model what to produce, validates what comes back, and powers autocomplete
→ Your function signature becomes the tool definition
→ Validation errors become feedback the model can fix itself
→ It’s already in your stack (OpenAI, Anthropic, LangChain, FastAPI…)
Plus a quick look at Pydantic AI, which runs that whole loop for you.
Prompts are suggestions. Schemas are contracts. 🎯 After years of fixing #UiPath (https://www.linkedin.com/search/results/all/?keywords=%23uipath&origin=HASH_TAG_FROM_FEED) robots in production, I wrote down what I’ve learned about where AI agents really help in automation, and where they don't.
I’m Imad, a UiPath Automation Dev & AI Engineer. I spent years as an #RPA (https://www.linkedin.com/search/results/all/?keywords=%23rpa&origin=HASH_TAG_FROM_FEED) dev before AI agents became popular, and today I’m adding #Python (https://www.linkedin.com/search/results/all/?keywords=%23python&origin=HASH_TAG_FROM_FEED), #Playwright (https://www.linkedin.com/search/results/all/?keywords=%23playwright&origin=HASH_TAG_FROM_FEED), REST APIs and #LLMs (https://www.linkedin.com/search/results/all/?keywords=%23llms&origin=HASH_TAG_FROM_FEED) to that foundation.
I wrote about my journey in this article : https://www.linkedin.com/pulse/ai-engineer-from-uipath-rpa-agents-agentic-automation-berjamy-guv9e/ Support Request AI Agent: Hybrid GenAI Triage in UiPath NavIA: Prompt-Driven AI Browser Agent for UiPath & RPA